© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48613
    Prev
    Next
    INDEX
    Explanations

    God's love and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öh
    -0.95
    clero
    -0.90
     talisman
    -0.82
    SECTOR
    -0.79
    pray
    -0.78
    Geral
    -0.77
    realme
    -0.77
    ConfigService
    -0.77
    唐揚げ
    -0.76
    Materiale
    -0.76
    POSITIVE LOGITS
     loving
    1.19
     attributes
    1.11
     character
    1.05
     wrath
    1.05
    attribute
    1.02
     Attributes
    1.02
     sovereign
    1.01
     любовь
    1.00
     אה
    0.99
     infinite
    0.98
    Activations Density 0.015%

    No Known Activations